Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6423. Min Range: -8.6423
Max Act: 8.6423. Min Act: -0.1700
Data Index: 4519833 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6423. Min Range: -8.6423
Max Act: 8.2048. Min Act: -0.1700
Data Index: 3787523 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6423. Min Range: -8.6423
Max Act: 8.2048. Min Act: -0.1700
Data Index: 5329006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6423. Min Range: -8.6423
Max Act: 8.0798. Min Act: -0.1700
Data Index: 6025637 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.8923. Min Act: -0.1700
Data Index: 2585370 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.8298. Min Act: -0.1700
Data Index: 5567162 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.8923. Min Act: -0.1700
Data Index: 2207806 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.8298. Min Act: -0.1700
Data Index: 5986679 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 2665570 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 8222148 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.7048. Min Act: -0.1700
Data Index: 6130828 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 672873 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 4883993 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 8824366 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 7634684 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 5750490 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6111. Min Act: -0.1700
Data Index: 4338205 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.5798. Min Act: -0.1700
Data Index: 1351181 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.6111. Min Act: -0.1700
Data Index: 2911335 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6423. Min Range: -8.6423
Max Act: 7.5798. Min Act: -0.1700
Data Index: 7612859 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19